Hugging Face's logo

Best000
/
c1a76eb0-f51e-4a58-9199-7cc678469f29

PEFT
Safetensors
gpt_neo
axolotl
Generated from Trainer
Model card Files Community
c1a76eb0-f51e-4a58-9199-7cc678469f29
File size: 3,226 Bytes 
58bf0a3
 
 
6901c1b
58bf0a3
6901c1b
58bf0a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4211caf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1423ba2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6901c1b
 
 
 
 
 
 
58bf0a3
 
 
 
 
 
 
 
 
 
 
 
 
 
6901c1b
58bf0a3
 
 
 
6901c1b
58bf0a3
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000127712289753643,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2771228975364299e-05,
      "grad_norm": 1.6853578090667725,
      "learning_rate": 2e-05,
      "loss": 12.8567,
      "step": 1
    },
    {
      "epoch": 1.2771228975364299e-05,
      "eval_loss": 3.4389500617980957,
      "eval_runtime": 284.8559,
      "eval_samples_per_second": 115.739,
      "eval_steps_per_second": 57.871,
      "step": 1
    },
    {
      "epoch": 2.5542457950728598e-05,
      "grad_norm": 1.7145562171936035,
      "learning_rate": 4e-05,
      "loss": 12.9693,
      "step": 2
    },
    {
      "epoch": 3.8313686926092896e-05,
      "grad_norm": 1.7134019136428833,
      "learning_rate": 6e-05,
      "loss": 14.4764,
      "step": 3
    },
    {
      "epoch": 3.8313686926092896e-05,
      "eval_loss": 3.4378418922424316,
      "eval_runtime": 283.2099,
      "eval_samples_per_second": 116.412,
      "eval_steps_per_second": 58.208,
      "step": 3
    },
    {
      "epoch": 5.1084915901457196e-05,
      "grad_norm": 1.6709320545196533,
      "learning_rate": 8e-05,
      "loss": 13.5146,
      "step": 4
    },
    {
      "epoch": 6.38561448768215e-05,
      "grad_norm": 1.7994674444198608,
      "learning_rate": 0.0001,
      "loss": 12.8968,
      "step": 5
    },
    {
      "epoch": 7.662737385218579e-05,
      "grad_norm": 1.6614803075790405,
      "learning_rate": 0.00012,
      "loss": 13.3827,
      "step": 6
    },
    {
      "epoch": 7.662737385218579e-05,
      "eval_loss": 3.432285785675049,
      "eval_runtime": 283.3258,
      "eval_samples_per_second": 116.364,
      "eval_steps_per_second": 58.184,
      "step": 6
    },
    {
      "epoch": 8.93986028275501e-05,
      "grad_norm": 1.8888307809829712,
      "learning_rate": 0.00014,
      "loss": 14.1369,
      "step": 7
    },
    {
      "epoch": 0.00010216983180291439,
      "grad_norm": 1.870271921157837,
      "learning_rate": 0.00016,
      "loss": 13.645,
      "step": 8
    },
    {
      "epoch": 0.0001149410607782787,
      "grad_norm": 2.0643558502197266,
      "learning_rate": 0.00018,
      "loss": 14.1991,
      "step": 9
    },
    {
      "epoch": 0.0001149410607782787,
      "eval_loss": 3.406141757965088,
      "eval_runtime": 282.0298,
      "eval_samples_per_second": 116.899,
      "eval_steps_per_second": 58.451,
      "step": 9
    },
    {
      "epoch": 0.000127712289753643,
      "grad_norm": 2.1807892322540283,
      "learning_rate": 0.0002,
      "loss": 14.5287,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 21222716866560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}